lightweight-genai-stack/docker-compose.yml at main · schoolofdevops/lightweight-genai-stack · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
services:
  # Ollama - LLM Server (lightweight model)
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    deploy:
      resources:
        limits:
          memory: 3G  # Limit memory for Ollama (tinyllama is ~600MB)
    healthcheck:
      test: ["CMD", "ollama", "list"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 30s
    restart: unless-stopped

  # Model Puller - Downloads the lightweight model on startup
  model-puller:
    image: curlimages/curl:latest
    container_name: model-puller
    depends_on:
      ollama:
        condition: service_healthy
    entrypoint: ["/bin/sh", "-c"]
    command:
      - |
        echo "Waiting for Ollama to be ready..."
        sleep 5
        echo "Pulling tinyllama:1.1b model (ultra-lightweight, ~600MB)..."
        curl -X POST http://ollama:11434/api/pull -d '{"name": "tinyllama:1.1b"}'
        echo "Pulling nomic-embed-text for embeddings..."
        curl -X POST http://ollama:11434/api/pull -d '{"name": "nomic-embed-text"}'
        echo "Models downloaded successfully!"

  # ChromaDB - Lightweight Vector Database
  chromadb:
    image: chromadb/chroma:latest
    container_name: chromadb
    ports:
      - "8000:8000"
    volumes:
      - chroma_data:/chroma/chroma
    environment:
      - IS_PERSISTENT=TRUE
      - ANONYMIZED_TELEMETRY=FALSE
    deploy:
      resources:
        limits:
          memory: 512M
    restart: unless-stopped

  # GenAI App - Streamlit RAG Application
  genai-app:
    build:
      context: ./app
      dockerfile: Dockerfile
    container_name: genai-app
    ports:
      - "8501:8501"
    environment:
      - OLLAMA_BASE_URL=http://ollama:11434
      - CHROMA_HOST=chromadb
      - CHROMA_PORT=8000
      - LLM_MODEL=tinyllama:1.1b
      - EMBEDDING_MODEL=nomic-embed-text
    depends_on:
      ollama:
        condition: service_healthy
      chromadb:
        condition: service_started
    volumes:
      - ./app:/app
      - uploaded_docs:/app/uploads
    deploy:
      resources:
        limits:
          memory: 1G
    restart: unless-stopped

volumes:
  ollama_data:
  chroma_data:
  uploaded_docs:

networks:
  default:
    name: genai-network